Xitong Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xitong Zhang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Guangliang Liu
Michigan State University
4 shared publications- Kristen Marie Johnson
Michigan State University
3 shared publications Rongrong Wang
Michigan State University
3 shared publications- Zhiyu Xue
UC Santa Barbara
3 shared publications - Wen Xiong
Yunnan Normal University
2 shared publications - Xian Zhang
School of Information Science and Technology, Yunnan Normal University, Kunming, China
2 shared publications
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7103-7117
Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
Guangliang Liu, Zimo Qi, Xitong Zhang, Lei Jiang, Kristen Johnson. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7103-7117
Open AccessDiagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
Guangliang Liu, Zimo Qi, Xitong Zhang, Lei Jiang, Kristen Johnson. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 22 November 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (1) , 1-29
An integrated static and dynamic graph fusion approach for traffic flow prediction
- 22 November 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (1) , 1-29
An integrated static and dynamic graph fusion approach for traffic flow prediction
- Open Access
- 3 May 2024
- Published by Springer Nature in Research Square
An Integrated Static and Dynamic Graph Fusion Approach for Traffic Flow Prediction
The major challenge in accurate traffic flow prediction lies in effectively capturing the dynamic spatiotemporal correlations within the traffic system. In this paper, we propose a novel traffic flow prediction method based on the fusion of static and dynamic graphs. Firstly, a predefined graph structure is used as the initial static graph. Secondly, a temporal graph convolution module constructed in a data-driven manner is designed, further implementing a dynamic graph structure that varies with the input data, thoroughly constructing the spatial relations between traffic flow sequence data. Finally, specific spatial and temporal relations are modeled from the perspective of graphs, effectively merging static and dynamic spatial relations. The performance of our method was validated using two real public datasets, PEMS04 and PEMS08. Experimental results demonstrate that our model outperforms existing traffic flow prediction models by 9.32% in terms of prediction error when compared to 18 benchmark methods.
- 3 May 2024
- Published by Springer Nature in Research Square
Open AccessAn Integrated Static and Dynamic Graph Fusion Approach for Traffic Flow Prediction
The major challenge in accurate traffic flow prediction lies in effectively capturing the dynamic spatiotemporal correlations within the traffic system. In this paper, we propose a novel traffic flow prediction method based on the fusion of static and dynamic graphs. Firstly, a predefined graph structure is used as the initial static graph. Secondly, a temporal graph convolution module constructed in a data-driven manner is designed, further implementing a dynamic graph structure that varies with the input data, thoroughly constructing the spatial relations between traffic flow sequence data. Finally, specific spatial and temporal relations are modeled from the perspective of graphs, effectively merging static and dynamic spatial relations. The performance of our method was validated using two real public datasets, PEMS04 and PEMS08. Experimental results demonstrate that our model outperforms existing traffic flow prediction models by 9.32% in terms of prediction error when compared to 18 benchmark methods.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1843-1856
Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
Guangliang Liu, Milad Afshari, Xitong Zhang, Zhiyu Xue, Avrajit Ghosh, Bidhan Bashyal, Rongrong Wang, Kristen Johnson. Findings of the Association for Computational Linguistics ACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1843-1856
Open AccessTowards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
Guangliang Liu, Milad Afshari, Xitong Zhang, Zhiyu Xue, Avrajit Ghosh, Bidhan Bashyal, Rongrong Wang, Kristen Johnson. Findings of the Association for Computational Linguistics ACL 2024. 2024.
- Open Access
PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs
Networks are ubiquitous in many real-world applications (e.g., social networks encoding trust/distrust relationships, correlation networks arising from time series data). While many networks are signed or directed, or both, there is a lack of unified software packages on graph neural networks (GNNs) specially designed for signed and directed networks. In this paper, we present PyTorch Geometric Signed Directed (PyGSD), a software package which fills this gap. Along the way, we evaluate the implemented methods with experiments with a view to providing insights into which method to choose for a given task. The deep learning framework consists of easy-to-use GNN models, synthetic and real-world data, as well as task-specific evaluation metrics and loss functions for signed and directed networks. As an extension library for PyG, our proposed software is maintained with open-source releases, detailed documentation, continuous integration, unit tests and code coverage checks. The GitHub repository of the library is https://github.com/SherylHYX/pytorch_geometric_signed_directed.
Open AccessPyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs
Networks are ubiquitous in many real-world applications (e.g., social networks encoding trust/distrust relationships, correlation networks arising from time series data). While many networks are signed or directed, or both, there is a lack of unified software packages on graph neural networks (GNNs) specially designed for signed and directed networks. In this paper, we present PyTorch Geometric Signed Directed (PyGSD), a software package which fills this gap. Along the way, we evaluate the implemented methods with experiments with a view to providing insights into which method to choose for a given task. The deep learning framework consists of easy-to-use GNN models, synthetic and real-world data, as well as task-specific evaluation metrics and loss functions for signed and directed networks. As an extension library for PyG, our proposed software is maintained with open-source releases, detailed documentation, continuous integration, unit tests and code coverage checks. The GitHub repository of the library is https://github.com/SherylHYX/pytorch_geometric_signed_directed.
- Open Access
PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent
Fine-tuning pretrained language models (PLMs) for downstream tasks is a large-scale optimization problem, in which the choice of the training algorithm critically determines how well the trained model can generalize to unseen test data, especially in the context of few-shot learning. To achieve good generalization performance and avoid overfitting, techniques such as data augmentation and pruning are often applied. However, adding these regularizations necessitates heavy tuning of the hyperparameters of optimization algorithms, such as the popular Adam optimizer. In this paper, we propose a two-stage fine-tuning method, PAC-tuning, to address this optimization challenge. First, based on PAC-Bayes training, PAC-tuning directly minimizes the PAC-Bayes generalization bound to learn proper parameter distribution. Second, PAC-tuning modifies the gradient by injecting noise with the variance learned in the first stage into the model parameters during training, resulting in a variant of perturbed gradient descent (PGD). In the past, the few-shot scenario posed difficulties for PAC-Bayes training because the PAC-Bayes bound, when applied to large models with limited training data, might not be stringent. Our experimental results across 5 GLUE benchmark tasks demonstrate that PAC-tuning successfully handles the challenges of fine-tuning tasks and outperforms strong baseline methods by a visible margin, further confirming the potential to apply PAC training for any other settings where the Adam optimizer is currently used for training.
Open AccessPAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent
Fine-tuning pretrained language models (PLMs) for downstream tasks is a large-scale optimization problem, in which the choice of the training algorithm critically determines how well the trained model can generalize to unseen test data, especially in the context of few-shot learning. To achieve good generalization performance and avoid overfitting, techniques such as data augmentation and pruning are often applied. However, adding these regularizations necessitates heavy tuning of the hyperparameters of optimization algorithms, such as the popular Adam optimizer. In this paper, we propose a two-stage fine-tuning method, PAC-tuning, to address this optimization challenge. First, based on PAC-Bayes training, PAC-tuning directly minimizes the PAC-Bayes generalization bound to learn proper parameter distribution. Second, PAC-tuning modifies the gradient by injecting noise with the variance learned in the first stage into the model parameters during training, resulting in a variant of perturbed gradient descent (PGD). In the past, the few-shot scenario posed difficulties for PAC-Bayes training because the PAC-Bayes bound, when applied to large models with limited training data, might not be stringent. Our experimental results across 5 GLUE benchmark tasks demonstrate that PAC-tuning successfully handles the challenges of fine-tuning tasks and outperforms strong baseline methods by a visible margin, further confirming the potential to apply PAC training for any other settings where the Adam optimizer is currently used for training.
- Open Access
Can Directed Graph Neural Networks be Adversarially Robust?
The existing research on robust Graph Neural Networks (GNNs) fails to acknowledge the significance of directed graphs in providing rich information about networks' inherent structure. This work presents the first investigation into the robustness of GNNs in the context of directed graphs, aiming to harness the profound trust implications offered by directed graphs to bolster the robustness and resilience of GNNs. Our study reveals that existing directed GNNs are not adversarially robust. In pursuit of our goal, we introduce a new and realistic directed graph attack setting and propose an innovative, universal, and efficient message-passing framework as a plug-in layer to significantly enhance the robustness of GNNs. Combined with existing defense strategies, this framework achieves outstanding clean accuracy and state-of-the-art robust performance, offering superior defense against both transfer and adaptive attacks. The findings in this study reveal a novel and promising direction for this crucial research area. The code will be made publicly available upon the acceptance of this work.
Open AccessCan Directed Graph Neural Networks be Adversarially Robust?
The existing research on robust Graph Neural Networks (GNNs) fails to acknowledge the significance of directed graphs in providing rich information about networks' inherent structure. This work presents the first investigation into the robustness of GNNs in the context of directed graphs, aiming to harness the profound trust implications offered by directed graphs to bolster the robustness and resilience of GNNs. Our study reveals that existing directed GNNs are not adversarially robust. In pursuit of our goal, we introduce a new and realistic directed graph attack setting and propose an innovative, universal, and efficient message-passing framework as a plug-in layer to significantly enhance the robustness of GNNs. Combined with existing defense strategies, this framework achieves outstanding clean accuracy and state-of-the-art robust performance, offering superior defense against both transfer and adaptive attacks. The findings in this study reveal a novel and promising direction for this crucial research area. The code will be made publicly available upon the acceptance of this work.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 12178-12189
PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent
Guangliang Liu, Zhiyu Xue, Xitong Zhang, Kristen Johnson, Rongrong Wang. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 12178-12189
Open AccessPAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent
Guangliang Liu, Zhiyu Xue, Xitong Zhang, Kristen Johnson, Rongrong Wang. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- Open Access
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (01) , 1194-1201
Shoreline: Data-Driven Threshold Estimation of Online Reserves of Cryptocurrency Trading Platforms
With the proliferation of blockchain projects and applications, cryptocurrency exchanges, which provides exchange services among different types of cryptocurrencies, become pivotal platforms that allow customers to trade digital assets on different blockchains. Because of the anonymity and trustlessness nature of cryptocurrency, one major challenge of crypto-exchanges is asset safety, and all-time amount hacked from crypto-exchanges until 2018 is over $1.5 billion even with carefully maintained secure trading systems. The most critical vulnerability of crypto-exchanges is from the so-called hot wallet, which is used to store a certain portion of the total asset of an exchange and programmatically sign transactions when a withdraw happens. Whenever hackers managed to gain control over the computing infrastructure of the exchange, they usually immediately obtain all the assets in the hot wallet. It is important to develop network security mechanisms. However, the fact is that there is no guarantee that the system can defend all attacks. Thus, accurately controlling the available assets in the hot wallets becomes the key to minimize the risk of running an exchange. However, determining such optimal threshold remains a challenging task because of the complicated dynamics inside exchanges. In this paper, we propose Shoreline, a deep learning-based threshold estimation framework that estimates the optimal threshold of hot wallets from historical wallet activities and dynamic trading networks. We conduct extensive empirical studies on the real trading data from a trading platform and demonstrate the effectiveness of the proposed approach.
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (01) , 1194-1201
Open AccessShoreline: Data-Driven Threshold Estimation of Online Reserves of Cryptocurrency Trading Platforms
With the proliferation of blockchain projects and applications, cryptocurrency exchanges, which provides exchange services among different types of cryptocurrencies, become pivotal platforms that allow customers to trade digital assets on different blockchains. Because of the anonymity and trustlessness nature of cryptocurrency, one major challenge of crypto-exchanges is asset safety, and all-time amount hacked from crypto-exchanges until 2018 is over $1.5 billion even with carefully maintained secure trading systems. The most critical vulnerability of crypto-exchanges is from the so-called hot wallet, which is used to store a certain portion of the total asset of an exchange and programmatically sign transactions when a withdraw happens. Whenever hackers managed to gain control over the computing infrastructure of the exchange, they usually immediately obtain all the assets in the hot wallet. It is important to develop network security mechanisms. However, the fact is that there is no guarantee that the system can defend all attacks. Thus, accurately controlling the available assets in the hot wallets becomes the key to minimize the risk of running an exchange. However, determining such optimal threshold remains a challenging task because of the complicated dynamics inside exchanges. In this paper, we propose Shoreline, a deep learning-based threshold estimation framework that estimates the optimal threshold of hot wallets from historical wallet activities and dynamic trading networks. We conduct extensive empirical studies on the real trading data from a trading platform and demonstrate the effectiveness of the proposed approach.